unity-cli-skill
AGENTS.md2 starsChanged 3 months agoMITView on GitHub
This directory contains a field-tested playbook for driving the Unity Editor through the official Unity CLI (unity command + the com.unity.pipeline package). Before performing any Unity Editor operation, read SKILL.md in this directory and follow its rules — mode decision tree (connected vs. headless), command syntax, eval batching, safety rails (confirm/dry_run), and the verified known-issues table. References: - references/pipeline-commands.md — all 140 built-in editor commands, grouped by domain - references/eval-snippets.md — high-frequency C# eval snippets Quick sanity check that the…
In this repositoryOne other file it gives its agents.
- unity-cliSkill
The file
Files
Unity Editor automation via the official Unity CLI
This directory contains a field-tested playbook for driving the Unity Editor
through the official Unity CLI (unity command + the com.unity.pipeline package).
Before performing any Unity Editor operation, read SKILL.md in this directory
and follow its rules — mode decision tree (connected vs. headless), command syntax,
eval batching, safety rails (confirm/dry_run), and the verified known-issues table.
References:
references/pipeline-commands.md— all 140 built-in editor commands, grouped by domainreferences/eval-snippets.md— high-frequency C# eval snippets
Quick sanity check that the toolchain is up:
unity status --format json # lists connected editor instances (Pipeline server :7800)Prerequisites (once per machine/project): install the Unity CLI, unity auth login,
then unity pipeline install --project-path <project>. Details in README.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.